© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17861
    Prev
    Next
    INDEX
    Explanations

    phrases related to strength and empowerment

    oai_token-act-pair · gpt-3.5-turbo

    references to strength and resilience, particularly in the context of physical or metaphorical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inea
    -0.97
     Wonderland
    -0.93
     Deaths
    -0.79
    çīĪ
    -0.72
     Loft
    -0.71
     Pablo
    -0.71
    tainment
    -0.71
     hereafter
    -0.71
     entertain
    -0.70
    ocide
    -0.69
    POSITIVE LOGITS
    Weak
    1.04
     resolve
    0.91
     shoulders
    0.91
     withstand
    0.88
     muscles
    0.88
     weakest
    0.84
     foothold
    0.83
    weak
    0.82
     laure
    0.82
     defenses
    0.82
    Activations Density 0.324%

    No Known Activations